Presentation	2010-01-18 On learning characteristics of binary neural networks with fuzziness tolerance Syutaro KABEYA, Toshimichi SAITO,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	This paper applies the genetic algorithm (GA) to the binary neural networks (BNN) with fuzziness tolerance and studies learning characteristics. A GA based learning is suitable to reduce the number of hidden neurons and to tolerate noise and outliers. We change the number of genes which have possibility of mutation in GA. We think it settles to the optimum solution fast because it increases rate of random. Performing basic numerical experiment, the algorithm effciency is confirmed.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Binary Neural Networks / Genetic Algorithm / Mutation
Paper #	NC2009-79
Date of Issue

Conference Information
Committee	NC
Conference Date	2010/1/11(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Neurocomputing (NC)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	On learning characteristics of binary neural networks with fuzziness tolerance
Sub Title (in English)
Keyword(1)	Binary Neural Networks
Keyword(2)	Genetic Algorithm
Keyword(3)	Mutation
1st Author's Name	Syutaro KABEYA
1st Author's Affiliation	Department of Electrical and Electronics Engineering, Hosei University()
2nd Author's Name	Toshimichi SAITO
2nd Author's Affiliation	Department of Electrical and Electronics Engineering, Hosei University
Date	2010-01-18
Paper #	NC2009-79
Volume (vol)	vol.109
Number (no)	363
Page	pp.pp.-
#Pages	6
Date of Issue